Covers the Luma Dream Machine API so Claude Desktop can create videos and images with Luma AI.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add luma-ai --env LUMA_API_KEY='<LUMA_API_KEY>' -- uv run --project /path/to/your/luma-ai-mcp-server -m luma_ai_mcp_server~/.codex/config.toml
[mcp_servers.luma-ai]
command = "uv"
args = ["run", "--project", "/path/to/your/luma-ai-mcp-server", "-m", "luma_ai_mcp_server"]
env = { LUMA_API_KEY = "<LUMA_API_KEY>" }
# codex mcp add luma-ai --env LUMA_API_KEY='<LUMA_API_KEY>' -- uv run --project /path/to/your/luma-ai-mcp-server -m luma_ai_mcp_server~/.cursor/mcp.json
{
"mcpServers": {
"luma-ai": {
"command": "uv",
"args": [
"run",
"--project",
"/path/to/your/luma-ai-mcp-server",
"-m",
"luma_ai_mcp_server"
],
"env": {
"LUMA_API_KEY": "<LUMA_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"luma-ai": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"--project",
"/path/to/your/luma-ai-mcp-server",
"-m",
"luma_ai_mcp_server"
],
"env": {
"LUMA_API_KEY": "<LUMA_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"luma-ai": {
"command": "uv",
"args": [
"run",
"--project",
"/path/to/your/luma-ai-mcp-server",
"-m",
"luma_ai_mcp_server"
],
"env": {
"LUMA_API_KEY": "<LUMA_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"luma-ai": {
"command": "uv",
"args": [
"run",
"--project",
"/path/to/your/luma-ai-mcp-server",
"-m",
"luma_ai_mcp_server"
],
"env": {
"LUMA_API_KEY": "<LUMA_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"luma-ai": {
"command": "uv",
"args": [
"run",
"--project",
"/path/to/your/luma-ai-mcp-server",
"-m",
"luma_ai_mcp_server"
],
"env": {
"LUMA_API_KEY": "<LUMA_API_KEY>"
}
}
}
}Environment variables
LUMA_API_KEY
Replace the placeholders with your own credentials and keep them out of version control.